biondizzle/DeepGEMM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Make various updates and fixes: (#164)

Browse Source 
- Add BF16 support for SM90 and SM100
- Refactor Python APIs
- Other fixes and code refactoring
This commit is contained in:
Ray Wang
2025-08-15 18:32:35 +08:00
committed by GitHub
parent 3254b758e2
commit f85ec649d7
34 changed files with 2293 additions and 495 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
csrc/jit/compiler.hpp
View File

@@ -35,10 +35,10 @@ public:
}
static void prepare_init(const std::string& library_root_path,
const std::string& cuda_home_path_by_torch) {
const std::string& cuda_home_path_by_python) {
Compiler::library_root_path = library_root_path;
Compiler::library_include_path = Compiler::library_root_path / "include";
Compiler::cuda_home = cuda_home_path_by_torch;
Compiler::cuda_home = cuda_home_path_by_python;
Compiler::library_version = get_library_version();
}
@@ -64,6 +64,8 @@ public:
get_env<int>("DG_JIT_CPP_STANDARD", 20));
if (get_env("DG_JIT_DEBUG", 0) or get_env("DG_JIT_PTXAS_VERBOSE", 0))
flags += " --ptxas-options=--verbose";
if (get_env("DG_JIT_WITH_LINEINFO", 0))
flags += " -Xcompiler -rdynamic -lineinfo";
}
virtual ~Compiler() = default;